Faults Diagnosis of a Girth Gear using Discrete Wavelet ...admt.iaumajlesi.ac.ir/article_534895_7ed478eb9b299e3a2d8abefd7e6f3ea5.pdfAbstract: In this paper, a fault diagnosis system
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
Int J Advanced Design and Manufacturing Technology, Vol. 7/ No. 3/ September - 2014 45
Received: 25 February 2014, Revised: 22 July 2014, Accepted: 13 August 2014
Abstract: In this paper, a fault diagnosis system based on discrete wavelet transform (DWT) and artificial neural networks (ANNs) was designed to diagnose different types of faults in gears. DWT is an advanced signal-processing technique for fault detection and identification. Five features of wavelet transform RMS, crest factor, kurtosis, standard deviation and skewness of discrete wavelet coefficients of normalized vibration signals have been selected. These features are considered as the feature vector for training purpose of the ANN. A wavelet selection criteria, namely Maximum Energy to Shannon Entropy ratio, was used to select an appropriate mother wavelet and discrete level, for feature extraction. To ameliorate the algorithm, various ANNs were exploited to optimize the algorithm so as to determine the best values for “number of neurons in hidden layer” resulted in a high-speed, meticulous three-layer ANN with a small-sized structure. The diagnosis success rate of this ANN was 100% for experimental data set. An experimental set of data has been used to verify the effectiveness and accuracy of the proposed method. To develop this method in general fault diagnosis application, an example was investigated in cement industry. At first, a MLP network with well-formed and optimized structure (20:12:3) and remarkable accuracy was presented providing the capability to identify different faults of gears. Then this neural network with optimized structure was presented to diagnose different faults of gears. The performance of the neural networks in learning, classifying and general fault diagnosis were found encouraging and can be concluded that neural networks have high potentiality in condition monitoring of the gears with various faults.
Reference: Akbari, M., Homaei, H., and Heidari, M., “Faults Diagnosis of a Girth Gear using Discrete Wavelet Transform and Artificial Neural Networks”, Int J of Advanced Design and Manufacturing Technology, Vol. 7/ No. 3, 2014, pp. 37-47.
Biographical notes: H. Homaei is Associate Professor of Mechanical engineering at the University of Shahrekord, Iran. He received his PhD in Mechanical engineering from Isfahan University, Isfahan, and BSc from Sharif University of Technology, Tehran, Iran. His current research focuses on condition monitoring of rotary equipment. M. Heidari received his MSc in Mechanical Engineering from Shahid Chamran University of Ahvaz in 2003. He is currently instructor at the Department of Mechanical Engineering, Abadan Branch, Islamic Azad University, Abadan, Iran. His current research interest includes Condition Monitoring and Fault Diagnosis. M. Akbari is an engineer in Sepahan Cement Co. Industry. He received his MSc in Mechanical Engineering from Shahrekord University.
Table 4 Total performance of ANN classifiers with different
number of hidden-layer neurons
No. of hidden-layer neurons
21 18 15 12 9 6
100% 100% 100% 100% 93% 93%
Results of
correct
fault
diagnosis%
6.2. Fault diagnosis on girth gear
In this example vibration signal of a girth gear is
checked. This girth gear is used to rotate a ball mill in
cement industry. Table 5 shows characteristics of this
large gear. A vibration signal was collected on journal
bearing of its pinion. The designed neural network was
used for this girth gear trouble shooting. For this
purpose the feature vector was extracted from vibration
signal and applied to the neural network. Diagnostic
results indicated breakage and wear of the teeth. The
accuracy of the result was confirmed after girth gear
inspection.
Table 5 Girth gear and pinion characteristics
Outer
diameter
Module Teeth
no.
Speed(RPM)
7200mm 30 238 15 Girth
gear
990mm 30 31 115 Pinion
7 CONCLUSION
This paper has outlined the definition of the discrete
wavelets transform and then demonstrated how it can
be applied to the analysis of the vibration signals
produced by gears in various conditions and faults. A
wavelet selection criterion "Maximum Energy to
Shannon Entropy ratio" was used to select an
appropriate wavelet and Bi-orthogonal wavelet
(bior3.1) was selected for feature extraction. Five
statistical features (Root mean square (RMS) value,
crest factor, kurtosis, skewness, standard deviation)
were extracted for all the approximation and details
coefficients of DWT.
These features were fed as input to neural network for
classification of various faults of the gears. A MLP
network with well-formed and optimized structure
(20:12:3) and remarkable accuracy was presented
providing the capability to identify different gears
faults. The performance of the neural network in
learning, classifying and general fault diagnosis were
found encouraging and can be concluded that neural
networks and wavelet transform have high potentiality
in condition monitoring of the gears with various faults.
REFERENCES
[1] Wu, J. D., Hsu, C. C., “Fault Gear Identification Using Vibration Signal with Discrete Wavelet Transform Technique and Fuzzy-Logic Inference”, Expert Systems with Applications, Vol. 36, No. 2, 2009, pp. 3785-3794.
[2] Rafiee, J., Arvani, F., Harifi, A., and Sadeghi, M. H., “Intelligent Condition Monitoring of a Gearbox Using Artificial Neural Network”, Mechanical Systems and Signal Processing, Vol. 21, 2007, pp. 1746-1754.
[3] Samantha, B., Al-Balushi, K. R., “Artificial Neural Networks Based Fault Diagnostics of Rolling Element Bearings Using Time Domain Features”, Mechanical Systems and Signal Processing, Vol. 17, 2003, pp. 317-328.
[4] Yang, Y., Dejie, Y., and Cheng, J., “A Fault Diagnosis Approach for Roller Bearing Based on IMF Envelope Spectrum and SVM”, Measurement, Vol. 40, 2007, pp. 943-950.
[5] Yuan, S., Chu, F., “Fault Diagnosis Based on Support Vector Machines with Parameter Optimization by Artificial Immunization Algorithm”, Mechanical Systems and Signal Processing, Vol. 21, 2007, pp. 1318-1330.
[6] Finley, W. R., Hodowance, M. M., and Holter, W. G., “An Analytical Approach to Solving Motor Vibration Problems”, IEEE Transactions on Industry Applications, Vol. 36, No. 5, 2000, pp. 1467-1480.
[7] Lei, Y., He, Z., and Zi, Y., “Application of an Intelligent Classification Method to Mechanical Fault Diagnosis”, Expert Systems with Applications, Vol. 36, 2009, pp. 9941-9948.
[8] Saravanan, N., Kumar, V. N. S., and Ramachandran, K. I., “A Comparative Study on Classification of Features by SVM and PSVM Extracted Using Morlet Wavelet for Fault Diagnosis”, Expert Systems with Applications, Vol. 35, 2008, pp.1351-1366.
[9] Xian, G., Zeng, B., “An Intelligent Fault Diagnosis Method Based on Wavelet Packet Analysis and Hybrid Support Vector Machine”, Expert Systems with applications, Vol. 22, 2009, pp. 1048-1060.
[10] Paya, B. A., Esat, I. I., and Badi, M. N. M., “Artificial Neural Networks Based Fault Diagnostics of Rotating Machinery Using Wavelet Transforms as a Preprocessor”, Mechanical Systems and Signal Processing, Vol. 11, 1997, pp.751-765.
[11] Staszewski, W. J., Tomlinson, G. R., “Application of the Wavelet Transforms to Fault Detection in Spur Gear”, Mechanical Systems and Signal Processing, Vol. 8, 1994, pp. 289-307.
[12] Abbasion, S., Rafsanjani, A., Farshidianfar, A., and Irani, N., “Rolling Element Bearings Multi-Fault Classification Based on the Wavelet Denoising and Support Vector Machine”, Mechanical Systems and Signal Processing, Vol. 21, 2007, pp. 2933-2945.
[13] Prabhakar, S., Mohanty, A. R., and Sekhar, A. S., “Application of Discrete Wavelet Transform for Detection of Ball Bearing Race Faults”, Tribology International, Vol. 35, 2002, pp. 793-800.
[14] Gao, X. Z., Ovaska, S. J., “Soft Computing Methods in Motor Fault Diagnosis”, Applied Soft Computing, Vol. 1, 2001, pp. 73-81.
Int J Advanced Design and Manufacturing Technology, Vol. 7/ No. 3/ September - 2014 55
[15] Yan, R., “Base Wavelet Selection Criteria for Non-Stationary Vibration Analysis in Bearing Health Diagnosis”, Electronic Doctoral Dissertations for UMass Amherst, Paper AAI3275786, http://scholarworks.umass.edu/dissertations/AAI3275786, January 1, 2007.
[17] Peng, Z. K., Chu, F. L., “Application of the Wavelet Transform in Machine Condition Monitoring and Fault Diagnostics: A Review with Bibliography”, Mechanical Systems and Signal Processing, Vol. 18, 2004, pp.199-221.
[18] Wang, W. J., “Applications of Wavelets to Gearbox Vibration Signals for Fault Detection”, Journal of Sound and Vibration Vol. 192, No. 5, 1996, pp. 927-939.
[19] Mori, K., Kasashima, N., Yoshioka, T., and Ueno, Y., “Prediction of Spalling on Ball Bearing by Applying the Discrete Wavelet Transform to Vibration Signals”, Wear, Vol. 195, 1996, pp.162-168.
[20] Mallat, S., “A Wavelet Tour of Signal Processing”, Academic Press, New York, 1998.
[21] Rafiee, J., Tse, P. W., Harifi, A., and Sadeghi, M. H., “A Novel Technique for Selecting Mother Wavelet Function Using an Intelligent Fault Diagnosis”,
Expert Systems with Applications, Vol. 37, 2010, pp. 4168-4181.
[22] Saravanan, N., Ramachandran, K. I., “Incipient Gearbox Fault Diagnosis Using Discrete Wavelet Transform (DWT) for Feature Extraction and Classification Using Artificial Neural Network (ANN)”, Expert Systems with Applications, Vol. 37, 2010, pp. 4168-4181.
[23] Zhang, J., Walter, G. G., Miao, Y., and Lee, W. N. W., “Wavelet Neural Networks for Function Learning”, IEEE Transactions on Signal Processing, Vol. 43, 1995, pp.1485-1497.
[24] Barakat, M., Druaux, F., Lefebvre, D., Khalil, M., and Mustapha, O., “Self Adaptive Growing Neural Network Classifier for Faults Detection and Diagnosis”, Neurocomputing, Vol. 74, 2011, pp. 3865-3876.
[25] Kankar, P. K., Satish, C. S., and Harsha, S. P., “Fault Diagnosis of Ball Bearings Using Continuous Wavelet Transform”, Applied Soft Computing, Vol. 11, 2011, pp. 2300-2312.
[26] Hajnayeb, A., Ghasemloonia, A., Khadem, S. E., and Moradi, M. H., “Application and Comparison of an ANN-based Feature Selection Method and the Genetic Algorithm in Gearbox Fault Diagnosis”, Expert Systems with Applications, Vol. 38, 2011, pp. 10205-10209.